CN114576564A - Artificial intelligent detecting system for blocking and leakage of sewer pipe and canal - Google Patents
Artificial intelligent detecting system for blocking and leakage of sewer pipe and canal Download PDFInfo
- Publication number
- CN114576564A CN114576564A CN202011373101.5A CN202011373101A CN114576564A CN 114576564 A CN114576564 A CN 114576564A CN 202011373101 A CN202011373101 A CN 202011373101A CN 114576564 A CN114576564 A CN 114576564A
- Authority
- CN
- China
- Prior art keywords
- water level
- leakage
- rainfall
- day
- curve
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 230000000903 blocking effect Effects 0.000 title claims description 19
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 305
- 238000011144 upstream manufacturing Methods 0.000 claims abstract description 12
- 230000002159 abnormal effect Effects 0.000 claims description 18
- 238000001914 filtration Methods 0.000 claims description 18
- 238000013473 artificial intelligence Methods 0.000 claims description 13
- 238000005259 measurement Methods 0.000 claims description 12
- 238000012935 Averaging Methods 0.000 claims description 6
- 238000012806 monitoring device Methods 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 claims description 2
- 230000002045 lasting effect Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 230000001105 regulatory effect Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 description 20
- 238000010586 diagram Methods 0.000 description 13
- 238000012423 maintenance Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 5
- 238000007689 inspection Methods 0.000 description 4
- 238000000034 method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000009434 installation Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 2
- 239000010865 sewage Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000008021 deposition Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 239000004519 grease Substances 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/02—Preventing, monitoring, or locating loss
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
An artificial intelligent detecting system for the blocked leakage of sewer pipe is composed of a sensor for acquiring the flow, flow speed and water level of sewer, a rainfall monitor for acquiring the rainfall and the rainfall, water level and flow of upstream and downstream pipes, and an intelligent arithmetic unit for artificial intelligent arithmetic to automatically detect the blocked leakage of sewer pipe.
Description
Technical Field
The invention relates to an artificial intelligent detection system for blocking and leakage of a sewer pipe, which is an automatic system for automatically detecting the blocking and leakage degree of the sewer pipe.
Background
The sewer pipe is buried under the ground in a closed pipeline, and the pipeline is often blocked by silting or foreign matters, so that the cross section is reduced to cause manhole overflow to cause flooding, or the pipeline is damaged and broken to cause leakage to cause environmental pollution. The reasons for the major abnormalities are as follows:
(1) the water delivery capacity of the pipe canal is insufficient, the gradient is poor, and the stratum sinks to cause that the water outlet is too high and cannot be discharged.
(2) The silting and blocking of the canal can reduce the section of flowing water because of the invasion of tree roots, the attachment of mixed soil blocks, the falling of water-stop rubber rings, the broken cloth and other floating objects in the storage tube, or the deposition of earth stones, sand dishes and the like in the tube because of the damage of the pipeline, or the adhesion of grease in sewage to the tube wall.
(3) The pipe canal is broken and leaked due to the change of the ground, damage caused by earthquake, damage caused by other engineering construction and the like.
The sewer is checked for blocking and leakage by using a camera to check the condition in the pipe section by section, and the pipe is recorded and interpreted as a main checking mode, and field operators carry video recording equipment to carry out longitudinal checking and perform circular shooting at each joint to confirm the condition of the pipeline. Or, the camera is set on the self-running vehicle device and moved in the pipeline, and the state of sewer damage, crack, leakage and connecting pipe is observed by the monitoring video recorder on the ground, and the state is recorded on the storage equipment and then is broadcast and checked.
However, the above inspection is disadvantageous in that inspection cannot be performed in a water-filled state, and therefore, it is necessary to clean the sewer system first and inspect the inspected pipe section after water is supplied thereto through another temporary pipe section, which is time-consuming and labor-consuming.
Therefore, if the above state occurs and the maintenance management is not proper, the problems of accumulated water and stink, sinking of the road, poor drainage and water flooding are easily caused. To prevent the accident, inspection and inspection should be performed frequently to maintain the normal function of the sewer facilities and to eliminate the occurrence of avoidable disasters in advance.
Disclosure of Invention
In order to solve the problems and detect the situations in real time, the invention uses an automatic detection system mechanism, can treat the problems caused by blockage and leakage of a sewer pipe in advance, and also directly arranges and positions a non-contact device in a manhole cover (the back of the manhole cover or the wall surface of the pipe) so as to effectively avoid the problems of corrosion of a sensing wire rod contacting a water body and blockage of garbage of the sewer, thereby being beneficial to equipment installation and maintenance.
An artificial intelligence detection system for blocking and leaking sewer pipes comprises: a host body, which is internally provided with a host circuit board; an antenna device electrically connected to the host circuit board for receiving and transmitting data; a sensing device electrically connected to the host circuit board for detecting water level, flow rate and flow data in the pipe; a rainfall monitoring device for obtaining rainfall data and transmitting the rainfall data to the host body; the intelligent operation device is electrically connected with the host circuit board or arranged on a cloud server, and can collect rainfall, water level, flow velocity or/and flow data for processing and interpretation so as to analyze whether blockage or leakage occurs in the pipe duct or not; when the water level in the pipe channel is judged to be abnormal with the flow rate or compared with a normal regular water level time sequence curve of corresponding rainfall during rainfall, whether the blockage or the leakage exists is estimated; a battery for providing the operation power supply for the above devices.
In a preferred embodiment, wherein the water level is suddenly increased and the flow rate is decreased, to determine whether the sewer downstream is blocked, the determination conditions are:
(current water level measurement-previous water level measurement) is greater than a threshold value;
(previous flow measurement-current flow measurement) is greater than the threshold; and
after a period of time (15 minutes) or more, downstream pipe blockage can be judged.
In a preferred embodiment, wherein the water level suddenly drops and the flow rate rises, for determining whether the sewer upstream leaks, the determination conditions are:
(previous water level measurement-current water level measurement) is greater than the threshold value;
(current flow measurement-previous flow measurement) is greater than the threshold; and
the leakage of the downstream canal can be judged after a period of time (15 minutes).
In a preferred embodiment, the comparison with the regular water level on sunny days is used to determine whether the downstream of the rainwater sewer is blocked, and the determination conditions are as follows:
collecting a large amount of water level big data, filtering the water level and other data of the abnormal pipe conduits with known blockage or leakage and the like, removing the water level data in the rainfall period, and only keeping the water level data in sunny days;
dividing the water level of the sunny day into four time intervals, namely Monday to Thursday, Friday, Saturday and Sunday;
averaging the water levels at the same time in each time interval to obtain the average water levels in all the time intervals;
forming a water level time sequence curve of a fine day rule by the average water levels of the four time intervals;
multiplying the time sequence curve of the regular water level in a clear day by a multiplying factor (such as 1.2 times) to define the time sequence curve as a water level threshold curve of a blockage regulation rule in a clear day, and when the measured water level exceeds the water level threshold curve of the blockage regulation rule in the clear day for a period of time (such as 15 minutes), judging the measured water level as a blockage; and when the water level exceeds the percentage of the regular water level time sequence curve in the sunny day, estimating the blocking degree.
In a preferred embodiment, the comparison with the regular water level on sunny days is used to determine whether the upstream of the rain sewer is leaking, and the determination conditions are as follows:
collecting a large amount of water level big data information, filtering the water level and other information of the known abnormal pipe canal such as blockage or leakage, removing the water level information during rainfall and only keeping the water level information in fine days;
dividing the water level of the sunny day into four time intervals, namely Monday to Thursday, Friday, Saturday and Sunday;
averaging the water levels at the same time in each time interval to obtain the average water levels in all time intervals;
combining the average water levels of the four time periods to form a water level time sequence curve of a sunny rule;
multiplying the time sequence curve of the water level of the fine day rule by a multiplying factor (such as 0.8 time) to define the time sequence curve as a threshold curve of the water level of the leakage rule of the fine day, and when the measured water level exceeds the threshold curve of the water level of the leakage rule of the fine day in the fine day, lasting for a period of time (such as 15 minutes) or more, judging the water level as leakage; and when the water level exceeds the percentage of the regular water level time sequence curve in the fine day, estimating the leakage degree.
In a preferred embodiment, the comparison with the regular water level on sunny days is used to determine whether the sewer downstream is blocked, and the determination condition is:
collecting a large amount of water level big data information, filtering the water level and other information of the known abnormal pipe canal such as blockage or leakage, removing the water level information during rainfall and only keeping the water level information in fine days;
estimating the regular water level time sequence curve in fine days by using artificial intelligence algorithm (such as LSTM, RNN, etc.);
multiplying the water level time sequence curve of the clear day rule by a multiplying factor (such as 1.2 times), and defining the curve as a water level threshold curve of the clear day blockage rule; when the water level exceeds a water level threshold curve of a blockage regulation rule in a sunny day, the water level is measured and lasts for a period of time (such as 15 minutes) or more, and the water level is judged to be blocked; and when the water level exceeds the percentage of the regular water level time sequence curve in the sunny day, estimating the blocking degree.
In a preferred embodiment, the comparison with the regular water level on sunny days is used to determine whether the upstream of the sewer is leaking, and the determination condition is:
collecting a large amount of water level big data information, filtering the water level and other information of the known abnormal pipe canal such as blockage or leakage, removing the water level information during rainfall and only keeping the water level information in fine days;
estimating the regular water level time sequence curve in fine days by using artificial intelligence algorithm (such as LSTM, RNN, etc.);
multiplying the time sequence curve of the normal regular water level in a fine day by a multiplying factor (such as 0.8 time), and defining the time sequence curve as a threshold curve of the leakage regular water level in a fine day; when the water level exceeds the water level threshold curve of the leakage rule in a fine day, the water level is measured and lasts for a period of time (such as 15 minutes) or more, and the water level can be judged to be leakage; and when the water level exceeds the percentage of the regular water level time sequence curve in the fine day, estimating the leakage degree.
In a preferred embodiment, the comparison with the water level at the raining time is used to determine whether the downstream of the sewer is blocked, and the determination conditions are as follows:
collecting rainfall and water level big data information of a large number of rainfall events, and filtering the water level and other information of the known abnormal pipe conduits such as blockage or leakage;
estimating the corresponding water level time sequence curve of the rainy day rule by using an artificial intelligent algorithm (such as LSTM, RNN and the like);
multiplying the normal water level time sequence curve of the normal rainy day rule of the corresponding rainfall by a multiplying factor (such as 1.2 times), and defining the time sequence curve as a water level threshold curve of the normal rainy day blockage rule;
when the rainfall occurs, the measured water level exceeds the water level threshold curve of the blockage regulation in the rainy day, and the blockage can be judged after the measured water level exceeds the water level threshold curve for a period of time (such as 15 minutes); and when the rainfall occurs, estimating the blocking degree according to the percentage of the measured water level exceeding the water level time sequence curve of the rainfall time law.
In a preferred embodiment, the comparison with the water level of the rain day rule in the rain day is used to determine whether the upstream of the sewer is leaking, and the determination condition is:
collecting rainfall and water level big data information of a large number of rainfall events, and filtering the water level and other information of the known abnormal pipe conduits such as blockage or leakage;
estimating the corresponding water level time sequence curve of the rain day rule by using an artificial intelligence algorithm (such as LSTM, RNN and the like);
multiplying the normal water level time sequence curve of the rain day rule of the corresponding rainfall by a multiplying factor (such as 0.8 time), and defining the time sequence curve as a water level threshold curve of the rain day leakage rule;
when raining, the measured water level is smaller than the water level threshold curve of the leakage rule in rainy days, and the measured water level is continued for a period of time (such as 15 minutes) or more, so that the measured water level is judged to be leakage; and when the rainfall occurs, estimating the leakage degree according to the percentage of the measured water level lower than the water level time sequence curve of the rainy day rule.
In a preferred embodiment, the sensing device is a non-contact sensing device or a contact sensing device for detecting water level, flow rate or flow data in the pipe.
In a preferred embodiment, the non-contact sensing device is a radar-based flow meter or a laser-based flow meter.
In a preferred embodiment, the main body and the sensing device are fixed on the back of a manhole cover body or the wall of the pipe channel.
In a preferred embodiment, the intelligent computing device collects the rainfall data from a rainfall detection device or from an antenna receiving cloud server.
Drawings
FIG. 1 is a schematic diagram of an artificial intelligent detection system for blocked leakage in sewer pipes according to the present invention;
FIG. 2 is a schematic diagram of hardware of the artificial intelligent detection system for blocked leakage in sewer pipe;
FIG. 3A is a schematic diagram of a first flow of blockage analysis of the artificial intelligent detection system for blocked leakage in sewer pipes and canals according to the present invention;
FIG. 3B is a schematic diagram of a second flow of blockage analysis of the artificial intelligent detection system for blocked leakage in sewer pipes and canals of the present invention;
FIG. 3C is a schematic diagram of a third flow of blockage analysis of the artificial intelligent detection system for blocked leakage in sewer pipes and canals according to the present invention;
FIG. 3D is a fourth flow chart illustrating the blockage analysis of the artificial intelligent detection system for blocked leakage in sewer pipes and canals according to the present invention;
FIG. 3E is a schematic view of a first process of leak analysis of the artificial intelligent detection system for blocked leaks in sewer pipes according to the present invention;
FIG. 3F is a schematic diagram of a second process for leak analysis of an artificial intelligent detection system for blocked leaks in sewer pipes according to the present invention;
FIG. 3G is a schematic diagram of a third flow of leakage analysis of the artificial intelligent detection system for blocked leakage in sewer pipes and canals according to the present invention;
FIG. 3H is a schematic diagram of a fourth process for leak analysis of an artificial intelligent detection system for blocked leaks in sewer pipes according to the present invention;
FIG. 4A is a schematic view of the artificial intelligent detection system for blocked leakage in sewer pipe, which is fixed on the back of the manhole cover;
FIG. 4B is a schematic view of the artificial intelligent detection system for the blocked leakage in sewer pipe, which is fixed on the wall of the sewer pipe;
FIG. 4C is a schematic view of the sensing device of the artificial intelligent detecting system for blocked and leaking sewer pipe and canal of the present invention installed outside the main body;
FIG. 5 is a schematic diagram of an external contact sensor of the artificial intelligent detecting system for blocking and leaking of sewer pipes and canals of the present invention;
FIG. 6A is a schematic view of an artificial intelligent detecting system for detecting the leakage of blocked sewer pipe and its antenna installed on the manhole cover;
FIG. 6B is a schematic diagram of a non-contact sensor as the sensing device of the artificial intelligent detecting system for blocked leakage in sewer pipe;
FIG. 6C is a schematic diagram of a hardware cross-section of an artificial intelligence detection system for blocked leakage in sewer pipes according to the present invention;
fig. 6D is a schematic diagram of the case and the cover of the artificial intelligent detecting system for blocked and leaked sewer pipes according to the present invention.
Description of the reference numerals
1: manhole cover body
11 front side
111 opening of the hole
114 locus of containment
1141 antenna device
11411 conducting wire of circuit
115 through a hole
12 back side
120 main unit body
121: case
1210 casing cover of computer case
1211 circuit board of host computer
1212 sensing device
1213A battery
1214 antenna device
1215, a contact sensor
1216 Intelligent arithmetic device
2: road surface
3: sewer well
4: rainfall monitoring equipment
51 cloud server
52 rain monitoring station
Upstream, downstream and associated pipe network monitoring equipment
54 remote control Unit
6, water body.
Detailed Description
Other technical matters, features and effects of the present invention will become apparent from the following detailed description of preferred embodiments, which proceeds with reference to the accompanying drawings.
Please refer to fig. 1 and 2, which are schematic diagrams of an artificial intelligence system for detecting leakage of blocked sewer pipes according to the present invention, and the system mainly includes a host body 120, wherein the host body 120 receives data from a sensing device 1212 and a rainfall monitoring device 4, and can receive data (including rainfall, water level, flow rate and/or flow rate) from a cloud server 51 or data (including rainfall, water level, flow rate and/or flow rate) from a plurality of remote rainfall monitoring stations 52 or data (including water level, flow rate or flow rate) from a plurality of upstream and downstream related pipe network monitoring devices 53 via an antenna device 1214.
The host body 120 at least includes a housing 121, a host circuit board 1211, a sensing device 1212, a battery 1213, an antenna device 1214 and an intelligent computing device 1216 are disposed in the housing 121, wherein the sensing device 1212, the battery 1213, the antenna device 1214 and the intelligent computing device 1216 are electrically connected to the host circuit board 1211.
The sensing device 1212 is a non-contact sensing device (not directly contacting with the detecting object) or a contact sensing device (directly contacting with the detecting object) for detecting data such as water level, flow rate, and/or air pressure in the sewer well, wherein the non-contact sensing device is a radar type flow meter or a laser type flow meter.
The battery 1213 is used to provide power for the operation of the host body 120 and other hardware devices, and the antenna 1214 is used to wirelessly receive external data (including rainfall, water level, flow rate or flow rate) to the host 1211 and/or the host 1211 for transmitting data to the remote control unit 54 via the antenna 1214.
The rainfall monitoring device 4 can be installed on site to collect rainfall data and transmit the rainfall data to the host computer body 120.
The intelligent computing device 1216 is disposed inside the host body 120 or in the cloud server 51, and if installed inside the host body 120, the host circuit board 1211 is electrically connected; the intelligent operation device 1216 will operate the received data of water level, flow rate, etc. and the rainfall data to determine whether the sewer pipe is blocked or leaked;
the operation of the intelligent computing device 1216 is described as follows:
(1) the intelligent computing device 1216 determines whether the pipe is blocked, based on the following conditions:
(a) the water level sudden increase and flow rate reduction judgment and analysis process is shown in fig. 3A:
i. (current water level measurement-previous water level measurement) is greater than threshold 301 a;
(previous flow measurement-current flow measurement) is greater than threshold 302 a;
for a period of time (15 minutes) or more, a downstream pipe blockage 303a may be determined.
(b) Comparing, judging and analyzing the flow with the regular water level time sequence curve in a fine day, as shown in fig. 3B:
i. collecting a large amount of water level big data information, filtering the water level information of the known blocked or leaked abnormal pipe canal, removing the water level information in the rainfall period, and only keeping the water level information 401a in sunny days;
ii, dividing the water level data of the sunny day into four time intervals, namely Monday to Thursday, Friday, Saturday and Sunday 402 a;
averaging the water levels at the same time in each time interval to obtain the average water levels in all time intervals to form a regular water level time sequence curve 403a in a sunny day;
iv, multiplying the time sequence curve of the regular water level in the sunny day by a multiplying factor (such as 1.2 times), and defining the time sequence curve as a threshold curve 404a of the regular water level in the sunny day;
v. when the water level exceeds the water level threshold curve of the blockage regulation in a fine day, the water level is measured for a period of time (such as 15 minutes) and the water level is judged to be blocked 405 a;
and vi, when the water level exceeds the percentage of the regular water level time sequence curve in the fine day, estimating the blockage degree 406 a.
(c) Comparing, judging and analyzing the flow with the time sequence curve of the regular water level in a fine day, as shown in fig. 3C:
i. collecting a large amount of water level big data information, filtering the water level and other information of the known abnormal pipe canal such as blockage or leakage, removing the water level information in the rainfall period, and only keeping the water level information 501a in the sunny days;
ii, estimating a regular water level time sequence curve 502a in sunny days by using an artificial intelligence algorithm (such as LSTM, RNN and the like);
multiplying the time sequence curve of the regular water level in the sunny day by a multiplying factor (such as 1.2 times), and defining the time sequence curve as a threshold curve 503a of the regular water level in the sunny day;
iv, when the water level exceeds the water level threshold curve of the blockage regulation in a fine day, the measured water level is continued for a period of time (such as 15 minutes) or more, and the measured water level is judged to be a blockage 504 a;
v. estimating the blockage 505a on a sunny day based on the percentage of the measured water level over the regular water level time sequence curve on a sunny day.
(d) Comparing, judging and analyzing the flow with the rainfall time-series curve of the regular water level, as shown in fig. 3D:
i. collecting rainfall and water level big data information of a large number of rainfall events, and filtering the water level and other information 601a of the known blocking or leakage and other abnormal pipe conduits;
ii, estimating a corresponding water level time sequence curve 602a of the rainy day rule by using an artificial intelligence algorithm (such as LSTM, RNN and the like);
multiplying the time sequence curve of the water level of the rainfall rule corresponding to the rainfall by a multiplying factor (such as 1.2 times) to define a water level threshold curve 603a of the rainfall blockage rule;
when the rainfall occurs, the measured water level exceeds a water level threshold curve regulated by the blockage in the rainy day, and the measured water level is continued for a period of time (such as 15 minutes) or more, so that the measured water level is judged to be blocked 604 a; and
v. when it rains, the blockage 605a is estimated based on the percentage of the measured water level over the regular water level time series curve on a rainy day.
(2) The intelligent computing device 1216 determines whether the pipe is leaking, the determination condition being:
(a) the flow of determining and analyzing sudden drop of water level and rising of flow rate is shown in fig. 3E:
i. (the previous water level measurement-the current water level measurement) is greater than the threshold 301 b;
(current flow measurement-previous flow measurement) is greater than threshold 302 b;
for a period of time (15 minutes) or more, an upstream canal leak 303b can be determined.
(b) Comparing, judging and analyzing the flow with the time sequence curve of the regular water level in a sunny day, as shown in fig. 3F:
i. collecting a large amount of water level big data information, filtering the water level and other information of the known pipe canal such as abnormity of blockage or leakage and the like, removing the water level information in the rainfall period, and only keeping the water level information in sunny days 401 b;
ii, dividing the water level data of the sunny day into four time intervals, namely Monday to Thursday, Friday, Saturday and Sunday 402 b;
iii, averaging the water levels at the same time in each time interval to obtain the average water levels in all the time intervals to form a water level time sequence curve 403b in a sunny day rule;
iv, multiplying the time sequence curve of the water level of the sunny rule by a multiplying factor (such as 0.8 time) to define a threshold curve 404b of the water level of the leakage rule of the sunny day;
v. when the water level exceeds the water level threshold curve of the leakage rule in a fine day, the water level is measured and lasts for a period of time (such as 15 minutes) or more, and the water level is judged to be leakage 405 b;
and vi, estimating the leakage degree 406b according to the percentage of the measured water level exceeding the regular water level time sequence curve in the sunny day.
(c) Comparing, judging and analyzing the flow with the time sequence curve of the regular water level in a sunny day, as shown in fig. 3G:
i. collecting a large amount of water level big data, and filtering the water level and other data of the pipe canal, such as the known abnormity of blockage or leakage, and the like, 501 b;
ii, estimating a regular water level time sequence curve 502b in sunny days by using an artificial intelligence algorithm (such as LSTM, RNN and the like);
multiplying the time sequence curve of the water level of the sunny rule by a multiplying factor (such as 0.8 time), and defining the time sequence curve as a threshold curve 503b of the water level of the leakage rule of the sunny day;
iv, when the water level exceeds the water level threshold curve of the leakage rule in a fine day, the measured water level is continued for a period of time (such as 15 minutes) or more, and the measured water level can be judged as leakage 504 b;
v. estimating the degree of leakage 505b on a sunny day based on the percentage of the measured water level over the regular water level time sequence curve on a sunny day.
(d) Comparing, judging and analyzing the flow with the time sequence curve of the water level of the rain day rule in the rainfall, as shown in fig. 3H:
i. collecting rainfall and water level big data information of a large number of rainfall events, and filtering the water level and other information 601b of the known abnormal pipe conduits such as blockage or leakage;
ii, estimating a corresponding rain day regular water level time sequence curve 602b in the rainfall by using an artificial intelligence algorithm (such as LSTM, RNN and the like);
multiplying the time sequence curve of the water level of the rain day rule corresponding to the rainfall by a multiplying factor (such as 0.8 time), and defining the time sequence curve as a threshold curve 603b of the water level of the rain day leakage rule;
when raining, the measured water level is smaller than the water level threshold curve of the leakage rule in rainy days, and the measured water level is continued for a period of time (such as 15 minutes) or more, and the measured water level can be judged as leakage 604 b; and
v. when it rains, the extent of leakage 605b is estimated based on the percentage of the measured water level below the regular water level time series curve on a rainy day.
The main body 120 can be attached to the back 12 of a manhole cover body 1, as shown in fig. 4A, or the main body 120 can be attached to the wall of the canal near the back of the manhole cover body, as shown in fig. 4B.
In addition, as shown in fig. 4C, the sensing device 1212 can be disposed separately from the housing 121 and positioned on the back surface 12 or the duct wall surface.
In addition, as shown in fig. 5, when the host circuit board 1211 is connected to a contact sensor 1215 (such as an ultrasonic flowmeter, a pressure-type water level meter, an ultrasonic flow rate meter or a water quality meter), the contact sensor 1215 has a sensing end (not shown), and the sensing end of the contact sensor 1215 is in contact with the water 6 in the sewer well, so as to detect the data of the flow rate, the water level, the flow rate and the water quality of the water 6 in the sewer pipe.
In addition, the antenna device 2 can be disposed outside the housing 121 and positioned on the back surface 12; the antenna can be externally embedded on the front surface 11 or externally connected to a voltage-withstanding antenna, as shown in fig. 6A, 6B and 6C, an accommodating portion 114 can be formed on the front surface 11, and the antenna device 1141 is disposed in the accommodating portion 114, and the circuit wire 11411 inside the antenna device 1141 can be electrically connected to the host circuit board 1211 through a through hole 115;
when installed in the sewer well 3 of the road surface 2, as shown in fig. 6B and 6C, the sensing device 1212 does not need to directly contact with the sewage in the sewer for easy installation and maintenance if it is a non-contact sensing device.
In practical implementation, as shown in fig. 6D, after the cover 1210 is covered on the casing 121, the casing 121 is locked on the back 12 of the manhole cover body 1.
As shown in fig. 6C, a contact sensor 1215 can be disposed at the joint of the manhole cover body 1 and the sewer manhole 3, and if the manhole cover body 1 is removed, the contact sensor 1215 can activate the host circuit board 1211 to automatically send an alarm and return the open state of the manhole cover.
Compared with other prior art, the artificial intelligent detection system for blocked leakage of sewer pipe channel provided by the invention has the following advantages:
1. the present invention uses an automatic detection system mechanism to deal with the problems caused by the blocking and leakage of the sewer pipe in advance.
2. The invention has great advantages for the installation and maintenance of the detection system for sewer flow, water level and pipe canal blockage and leakage.
3. The design of the invention is greatly helpful for cleaning and maintenance, and can effectively reduce the cost required by maintenance.
The present invention is not limited to the above embodiments, and those skilled in the art can understand the technical features and embodiments of the present invention and can not make any changes and modifications within the spirit and scope of the present invention.
Claims (10)
1. The utility model provides a system is listened to sewer pipe canal blocking seepage artificial intelligence which characterized in that includes:
a host body, which is internally provided with a host circuit board;
a rainfall monitoring device for obtaining rainfall data and transmitting the rainfall data to the host body;
an antenna device electrically connected to the host circuit board for receiving and transmitting data;
a sensing device electrically connected to the host circuit board for detecting water level, flow rate and flow data in the pipe;
the intelligent operation device is electrically connected with the host circuit board or arranged on a cloud server, and can collect rainfall, water level, flow velocity or/and flow data for processing and interpretation so as to analyze whether blockage or leakage occurs in the pipe duct or not; when the water level in the pipe channel is judged to be abnormal with the flow rate or compared with a normal regular water level time sequence curve of corresponding rainfall during rainfall, whether the blockage or the leakage exists is estimated;
a battery for providing the operation power supply for the above devices.
2. The system of claim 1, wherein the abnormal water level surge and flow rate decrease is used to determine whether the sewer downstream is blocked, and the determination is made by:
(current water level measurement-previous water level measurement) is greater than a threshold value;
(previous flow measurement-current flow measurement) is greater than the threshold; and
and (5) continuing for more than a period of time, and judging that the downstream pipe is blocked.
3. The system of claim 1, wherein the comparison with the regular water level in sunny days is used to determine whether the downstream of the sewer is blocked, and the determination conditions are as follows:
collecting a large amount of water level big data information, filtering the water level information of the known blocked or leaked abnormal pipe and duct, removing the water level information in the rainfall period, and only keeping the water level information in sunny days;
dividing the water level in a sunny day into four time intervals;
averaging the water levels at the same time in each time interval to obtain the average water levels in all time intervals;
forming a water level time sequence curve of a fine day rule by the average water levels of the four time intervals;
multiplying the time sequence curve of the water level of the clear day rule by the multiplying power to define the time sequence curve as a water level threshold curve of a blockage regulation rule in the clear day, and when the measured water level exceeds the water level threshold curve of the blockage regulation rule in the clear day, lasting for more than a period of time to judge that the water level is blocked; and
and when the water level exceeds the percentage of the regular water level time sequence curve on the sunny day, the blocking degree is estimated.
4. The system of claim 1, wherein the comparison with the regular water level in sunny days is used to determine whether the downstream of the sewer is blocked, and the determination conditions are as follows:
collecting a large amount of water level big data information, filtering the water level information of the known blocked or leaked abnormal pipe and duct, removing the water level information during rainfall and only keeping the water level information in sunny days;
estimating a regular water level time sequence curve in fine days by using an artificial intelligent algorithm;
multiplying the time sequence curve of the water level of the clear weather rule by the multiplying power to define a water level threshold curve of the blockage rule of the clear weather; when the water level exceeds a water level threshold curve of a blockage regulation rule in a fine day, the water level is measured and lasts for more than a period of time, and blockage is judged; and
and when the water level exceeds the percentage of the regular water level time sequence curve on the sunny day, the blocking degree is estimated.
5. The system of claim 1, wherein the comparison with normal regular water level during rainfall is used to determine whether the sewer downstream is blocked, and the determination condition is:
collecting rainfall and water level big data information of a large number of rainfall events, and filtering water level information of known blocking or leakage abnormal pipe channels;
estimating a corresponding normal water level time sequence curve of the rainy day rule by using an artificial intelligence algorithm;
multiplying the normal water level time sequence curve of the rain day rule corresponding to the rainfall by the multiplying power to define a water level threshold curve of the rain day blockage rule;
when the rainfall occurs, the measured water level exceeds a water level threshold curve regulated by the blockage rule in the rainy day, and the measured water level is continued for more than a period of time to judge that the water level is blocked; and
and when the rainfall occurs, estimating the blocking degree according to the percentage of the measured water level exceeding the water level time sequence curve of the rainy day rule.
6. The system of claim 1, wherein the water level suddenly drops and the flow rate rises to determine whether there is leakage upstream of the sewer, the determination being made by:
(previous water level measurement-current water level measurement) is greater than the threshold value;
(current flow measurement-previous flow measurement) is greater than the threshold;
and continuing for more than a period of time, and judging the leakage of the downstream pipe duct.
7. The system of claim 1, wherein the comparison with the regular water level in sunny days is used to determine whether the upstream of the sewer is leaking, and the determination condition is:
collecting a large amount of water level big data, filtering the water level data of the pipe canal with known blockage or leakage abnormality, removing the water level data in the rainfall period, and only keeping the water level data in sunny days;
dividing the water level in a sunny day into four time intervals;
averaging the water levels at the same time in each time interval to obtain the average water levels in all time intervals;
combining the average water levels of the four time periods to form a water level time sequence curve of a sunny rule;
multiplying the time sequence curve of the regular water level in a fine day by the multiplying power to define the time sequence curve as a threshold curve of the regular water level of the leakage in a fine day, and when the measured water level exceeds the threshold curve of the regular water level of the leakage in a fine day and lasts for more than a period of time, judging the leakage; and
and when the water level exceeds the percentage of the regular water level time sequence curve on the fine day, estimating the leakage degree.
8. The system of claim 1, wherein the comparison with the regular water level in sunny days is used to determine whether the upstream of the sewer is leaking, and the determination condition is:
collecting a large amount of water level big data, filtering water level data of known blocked or leaked abnormal canals, removing the water level data during rainfall and only keeping the water level data in sunny days;
estimating a regular water level time sequence curve in fine days by using an artificial intelligent algorithm;
multiplying the time sequence curve of the regular water level in a fine day by the multiplying power to define a threshold curve of the regular water level of the leakage in a fine day; when the water level exceeds a water level threshold curve of a leakage rule in a fine day, the water level is measured and continues for more than a period of time, and the leakage is judged; and
and when the water level exceeds the percentage of the regular water level time sequence curve on the fine day, estimating the leakage degree.
9. The system of claim 1, wherein the comparison with normal regular water level during rainfall is used to determine whether the upstream of the sewer is leaking, and the determination condition is:
collecting rainfall and water level big data information of a large number of rainfall events, and filtering water level information of known blocking or leakage abnormal pipe channels;
estimating a corresponding normal water level time sequence curve of the rainy day rule by using an artificial intelligence algorithm;
multiplying the normal water level time sequence curve of the rainy day with the corresponding rainfall by multiplying power to define a water level threshold curve of the rainy day leakage rule;
when the rain falls, measuring that the water level is smaller than a water level threshold curve of a rain-day leakage rule, and judging the water level to be leaked after the water level is continuously measured for more than a period of time; and
and when the rainfall occurs, estimating the leakage degree according to the percentage of the measured water level lower than the normal water level time sequence curve of the rainy day.
10. The system of claim 1, wherein the sensor is a non-contact sensor or a contact sensor for detecting water level, flow rate or flow data in the canal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011373101.5A CN114576564A (en) | 2020-11-30 | 2020-11-30 | Artificial intelligent detecting system for blocking and leakage of sewer pipe and canal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011373101.5A CN114576564A (en) | 2020-11-30 | 2020-11-30 | Artificial intelligent detecting system for blocking and leakage of sewer pipe and canal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114576564A true CN114576564A (en) | 2022-06-03 |
Family
ID=81766685
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011373101.5A Withdrawn CN114576564A (en) | 2020-11-30 | 2020-11-30 | Artificial intelligent detecting system for blocking and leakage of sewer pipe and canal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114576564A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2618171A (en) * | 2022-09-20 | 2023-11-01 | Stormharvester Ipr Ltd | Anomaly detection in wastewater networks |
| WO2024061986A1 (en) * | 2022-09-20 | 2024-03-28 | Stormharvester IPR Limited | Anomaly detection for wastewater assets with pumps in wastewater networks |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101042587A (en) * | 2006-03-22 | 2007-09-26 | 株式会社东芝 | Integrated supervision and diagnosis apparatus |
| CN203432650U (en) * | 2013-07-05 | 2014-02-12 | 张冬 | Sewer early-warning and monitoring system |
| CN203743864U (en) * | 2014-03-26 | 2014-07-30 | 于久凯 | Monitoring and early warning system for sewer |
| KR101456981B1 (en) * | 2014-05-09 | 2014-11-06 | (주)웹솔루스 | Water level monitoring system for sewerage |
| CN205655889U (en) * | 2016-05-25 | 2016-10-19 | 武汉新烽光电股份有限公司 | Low -power consumption municipal drainage pipe network real -time supervision device |
| CN107478273A (en) * | 2017-08-14 | 2017-12-15 | 武汉科技大学 | Based on embedded and technology of Internet of things sewer monitoring system and method |
| CN109406717A (en) * | 2017-08-17 | 2019-03-01 | 北京元正数据科技有限公司 | Downhole parameters detection system |
| CN110081318A (en) * | 2019-05-17 | 2019-08-02 | 南京管科智能科技有限公司 | A kind of pipe network monitor system |
| CN110488299A (en) * | 2019-08-01 | 2019-11-22 | 唐山哈船科技有限公司 | A kind of urban waterlogging sewer blockage detection system and detection method |
| CN111176175A (en) * | 2019-11-21 | 2020-05-19 | 南京鸿光环保科技有限公司 | Intelligent sewer monitoring system based on Internet of things technology |
| CN111780829A (en) * | 2020-06-19 | 2020-10-16 | 中国农业大学 | Blockage detection system and method for drainage well lid |
| CN111878712A (en) * | 2020-07-07 | 2020-11-03 | 恒天益科技（深圳）有限公司 | Method and system for monitoring uniform flow of pipe network |
-
2020
- 2020-11-30 CN CN202011373101.5A patent/CN114576564A/en not_active Withdrawn
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101042587A (en) * | 2006-03-22 | 2007-09-26 | 株式会社东芝 | Integrated supervision and diagnosis apparatus |
| CN203432650U (en) * | 2013-07-05 | 2014-02-12 | 张冬 | Sewer early-warning and monitoring system |
| CN203743864U (en) * | 2014-03-26 | 2014-07-30 | 于久凯 | Monitoring and early warning system for sewer |
| KR101456981B1 (en) * | 2014-05-09 | 2014-11-06 | (주)웹솔루스 | Water level monitoring system for sewerage |
| CN205655889U (en) * | 2016-05-25 | 2016-10-19 | 武汉新烽光电股份有限公司 | Low -power consumption municipal drainage pipe network real -time supervision device |
| CN107478273A (en) * | 2017-08-14 | 2017-12-15 | 武汉科技大学 | Based on embedded and technology of Internet of things sewer monitoring system and method |
| CN109406717A (en) * | 2017-08-17 | 2019-03-01 | 北京元正数据科技有限公司 | Downhole parameters detection system |
| CN110081318A (en) * | 2019-05-17 | 2019-08-02 | 南京管科智能科技有限公司 | A kind of pipe network monitor system |
| CN110488299A (en) * | 2019-08-01 | 2019-11-22 | 唐山哈船科技有限公司 | A kind of urban waterlogging sewer blockage detection system and detection method |
| CN111176175A (en) * | 2019-11-21 | 2020-05-19 | 南京鸿光环保科技有限公司 | Intelligent sewer monitoring system based on Internet of things technology |
| CN111780829A (en) * | 2020-06-19 | 2020-10-16 | 中国农业大学 | Blockage detection system and method for drainage well lid |
| CN111878712A (en) * | 2020-07-07 | 2020-11-03 | 恒天益科技（深圳）有限公司 | Method and system for monitoring uniform flow of pipe network |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2618171A (en) * | 2022-09-20 | 2023-11-01 | Stormharvester Ipr Ltd | Anomaly detection in wastewater networks |
| WO2024061986A1 (en) * | 2022-09-20 | 2024-03-28 | Stormharvester IPR Limited | Anomaly detection for wastewater assets with pumps in wastewater networks |
| WO2024061980A1 (en) * | 2022-09-20 | 2024-03-28 | Stormharvester IPR Limited | Anomaly detection in wastewater networks |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114576564A (en) | Artificial intelligent detecting system for blocking and leakage of sewer pipe and canal | |
| KR100855170B1 (en) | Sewer pipe monitoring system | |
| KR100828968B1 (en) | Method connected to gis for maintaining and managing sewage pipe and system with function thereof | |
| Goel et al. | Assessment of sediment deposition rate in Bargi Reservoir using digital image processing | |
| US20230251124A1 (en) | Permeable Pavement Monitoring System | |
| US20180119844A1 (en) | Apparatus And Method For Detection And Monitoring Of The Condition Of Pipeline Components | |
| US20210404167A1 (en) | Detecting vacuum presure and anomalous cylcing in a vacuum sewer system | |
| Beheshti et al. | Detection of extraneous water ingress into the sewer system using tandem methods–a case study in Trondheim city | |
| CN112037474A (en) | Multi-sensor hierarchical debris flow monitoring and early warning method, system and computer equipment | |
| CN107843714B (en) | Artificial rainfall simulation device for debris flow test | |
| TWI770695B (en) | Artificial Intelligence Detection System for Sewer Pipeline Blockage and Leakage | |
| KR20050078189A (en) | Sewer monitoring and data analyzing method | |
| JP2022082294A (en) | Pipe channel abnormality detection system, estimation device, learning model generation device, pipe channel abnormality detector, method for detecting abnormality in pipe channel, method for estimation, and method for generating learning model | |
| KR100538445B1 (en) | Total management/monitoring system for sewer and method thereof | |
| KR100869237B1 (en) | Method for predicting the amount of deposit in sewage pipe using cctv or regression analysis and sewage pipe maintaining and managing system with function thereof | |
| KR101659310B1 (en) | System and method for managing drain pipes | |
| TWI770859B (en) | Automatic sewer monitoring system for inflow and infiltration | |
| CN101169483B (en) | Geological calamity rainfall monitoring prealarmer | |
| KR102080066B1 (en) | System for monitoring illegal waste- water discharge | |
| CN107807225B (en) | Artificial rainfall simulation method for debris flow test | |
| CN113487048A (en) | Drainage tunnel operation safety monitoring and maintenance system and method | |
| CN115853093B (en) | Drainage pipe network dynamic detection method and system capable of identifying rain and sewage hybrid connection | |
| CN214540108U (en) | Rainfall meter capable of measuring surface runoff and automatic rainfall monitoring system | |
| CN114091870A (en) | Automatic assessment method and system for ecological environment of tunnel region | |
| Mierau et al. | Open Channel Flow Monitoring Under Small Water Surface Gradients |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220603 |
|
| WW01 | Invention patent application withdrawn after publication |